Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Once a week, I tell Antigravity (3.8-flash) to rewrite every code comment and documentation that was changed in the past week. Neither GPT nor Claude can write like a human.
 help



Neither can Gemini.

Gemini models have consistently been the best, by far, at writing and explaining.

Best against other AI output, still not even close to what a human would write.

Okay, describe one quirk of Gemini-ese that makes it stand out?

If you use it often enough, it becomes quite easy to tell. For one, when using it through the chat interface, it always congratulates me on my amazing insight in the first paragraph or at least has a very forthcoming tone. It also has a fetish for numbered lists whenever attempting to make a point, which usually contain 3 items, sometimes 2. It's also quite good at making relatively unhelpful ASCII diagrams on a semi-frequent basis.

That said, I do genuinely enjoy brainstorming with it, and these quirks are not really a hindrance. If anything, the sentiment in the first paragraph is quite useful to quickly get an insight about where I stand with my thoughts, relative to the available knowledge that Gemini has access to.




Consider applying for YC's Winter 2027 batch! Applications are open till November 2.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: